Word Embeddings for Wine Recommender Systems Using Vocabularies of Experts and Consumers

Christophe Cruz; Cyril Nguyen Van; Laurent Gautier

Word Embeddings for Wine Recommender Systems Using Vocabularies of Experts and Consumers

Christophe Cruz ¹ Cyril Nguyen Van Laurent Gautier ²

1 Le2i - Laboratoire Electronique, Informatique et Image [UMR6303]

2 MSH Dijon (MSHD) - Maison des Sciences de l'Homme de Dijon

Abstract : This vision paper proposes an approach to use the most advanced word embeddings techniques to bridge the gap between the discourses of experts and non-experts and more specifically the terminologies used by the two communities. Word embeddings makes it possible to find equivalent terms between experts and non-experts, by approach the similarity between words or by revealing hidden semantic relations. Thus, these controlled vocabularies with these new semantic enrichments are exploited in a hybrid recommendation system incorporating content-based ontology and keyword-based ontology to obtain relevant wines recommendations regardless of the level of expertise of the end user. The major aim is to find a non-expert vocabulary from semantic rules to enrich the knowledge of the ontology and improve the indexing of the items (i.e. wine) and the recommendation process.

Keywords : Recommander systems Wine Ontology Word embedding Semantics Terminology Expert Discourse

Document type :

Journal articles

Domain :

Humanities and Social Sciences / Linguistics

Complete list of metadatas

https://halshs.archives-ouvertes.fr/halshs-01872273
Contributor : Laurent Gautier <>
Submitted on : Tuesday, September 11, 2018 - 6:42:38 PM
Last modification on : Tuesday, April 2, 2019 - 2:39:41 AM
Long-term archiving on : Wednesday, December 12, 2018 - 3:51:09 PM

OJWT_2018v5i1n04_Cruz.pdf

Publisher files allowed on an open archive

Word Embeddings for Wine Recommender Systems Using Vocabularies of Experts and Consumers

File

Identifiers

Collections

Citation

Export

Metrics

72

207

Contact

Word Embeddings for Wine Recommender Systems Using Vocabularies of Experts and Consumers

File

Identifiers

Collections

Citation

Export

Share

Metrics

72

207

Contact